Karaoke avatar animation based on facial motion data

Patent metadata

Field	Value
Publication number	US-10019825-B2
Application number	US-201314125157-A
Country	US
Kind code	B2
Filing date	Jun 5, 2013
Priority date	Jun 5, 2013
Publication date	Jul 10, 2018
Grant date	Jul 10, 2018

Abstract

Apparatus, systems, media and/or methods may involve animating avatars. User facial motion data may be extracted that corresponds to one or more user facial gestures observed by an image capture device when a user emulates a source object. An avatar animation may be provided based on the user facial motion data. Also, script data may be provided to the user and/or the user facial motion data may be extracted when the user utilizes the script data. Moreover, audio may be captured and/or converted to a predetermined tone. Source facial motion data may be extracted and/or an avatar animation may be provided based on the source facial motion data. A degree of match may be determined between the user facial motion data of a plurality of users and the source facial motion data. The user may select an avatar as a user avatar and/or a source object avatar.

First claim

We claim:

1. An apparatus to animate an avatar comprising:
an image capture device;
a script module to present script data to a user that is to include text taken from speech made in a performance by a source object in media content;
a motion module to extract user facial motion data that corresponds to one or more user facial gestures observed by the image capture device when the user is to utilize the script data to verbalize the text taken from the speech made in the performance by the source object, wherein the user is to emulate the source object when the source object in the media content speaks in the performance; and
an avatar module to animate an avatar based on the user facial motion data.

2. The apparatus of claim 1 , wherein the image capture device is to include a camera of a mobile platform and one or more of the user facial gestures are to occur in a visual field of the camera.

3. The apparatus of claim 1 , wherein the motion module is to extract source facial motion data that corresponds to the source object of the script data, and wherein the avatar module is to animate the avatar based on the source facial motion data.

4. The apparatus of claim 1 , wherein the avatar module is to provide an avatar selected by the user to be utilized as one or more of a user avatar or a source object avatar.

5. The apparatus of claim 1 , further including:
a tone module to recognize user audio to be captured by an audio capture device and to convert the user audio to a predetermined tone, wherein the predetermined tone is to include one or more of a tone of the user to be heard when an avatar for the source object is to be animated, a tone of the source object when an avatar for the user is to be animated, or a tone representative of an avatar type when the avatar for the source object or the avatar for the user is to be animated;
a match module to analyze a degree of match between the user facial motion data and source facial motion data that corresponds to one or more source object facial gestures when the source object in the media content speaks in the performance;
a compilation module to combine an avatar animation of a plurality of users into a same media content, wherein each user of the plurality of users is to emulate a corresponding source object when the corresponding source object in the media content speaks in the performance; and
a communication module to communicate one or more of motion data, avatar data, script data, tone data, match data, or compilation data over a communication network.

6. At least one computer-readable medium comprising one or more instructions that when executed on a computing device cause the computing device to:
present script data to a user that is to include text taken from speech made in a performance by a source object in media content;
extract user facial motion data that corresponds to one or more user facial gestures observed by an image capture device when the user is to utilize the script data to verbalize the text taken from the speech made in the performance by the source object, wherein the user is to emulate the source object when the source object in the media content speaks in the performance; and
animate an avatar based on the user facial motion data.

7. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to capture one or more of the user facial gestures that are to occur in a visual field of a camera of a mobile platform.

8. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to recognize user audio captured by an audio capture device, wherein the user audio is to be generated by the verbalization of the text by the user, and to convert the user audio to a predetermined tone.

9. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to extract source facial motion data that corresponds to the source object of the script data and to animate the avatar based on the source facial motion data.

10. The at least one medium of claim 9 , wherein when executed the one or more instructions cause the computing device to extract the source facial motion data from media content that includes one or more of a music video or an animated movie in which the user is absent, wherein the source object is to include one or more of a performer or a character in the media content.

11. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to provide an avatar selected by the user to be utilized as one or more of a user avatar or a source object avatar, wherein the avatar is to include an image of the source object.

12. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to analyze a degree of match between the user facial motion data and source facial motion data that corresponds to one or more source object facial gestures when the source object in the media content speaks in the performance.

13. The at least one medium of claim 12 , wherein when executed the one or more instructions cause the computing device to determine the degree of match between user facial motion data of a plurality of users and the source facial motion data, wherein each user of the plurality of users is to emulate a corresponding source object when the corresponding source object in the media content speaks in the performance, and to assign a value based on each degree of match.

14. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to combine an avatar animation for a plurality of avatars into a same media content, wherein each user of a plurality of users is to emulate a corresponding source object when the corresponding source object in the media content speaks in the performance, and wherein the same media content is to be one of stored or rendered.

15. The at least one medium of claim 6 , wherein when executed the one or more instructions cause the computing device to communicate one or more of motion data, avatar data, script data, tone data, match data, or compilation data in real-time.

16. A method to animate an avatar comprising:
presenting script data to a user that includes text taken from speech made in a performance by a source object in media content;
extracting user facial motion data corresponding to one or more user facial gestures observed by an image capture device when the user utilizes the script data to verbalize the text taken from the speech made in the performance by the source object, wherein the user emulates the source object when the source object in the media content speaks in the performance; and
animating an avatar based on the user facial motion data.

17. The method of claim 16 , further including capturing one or more of the user facial gestures occurring in a visual field of a camera of a mobile platform.

18. The method of claim 16 , further including:
recognizing user audio captured by an audio capture device, wherein the user audio is generated by the verbalization of the text by the user; and
converting the user audio to a predetermined tone.

19. The method of claim 16 , further including:
extracting source facial motion data corresponding to the source object of the script data; and
animating the avatar based on the source facial motion data.

20. The method of claim 16 , further including p

Assignees

• Intel Corp

Inventors

• Li Wenlong
• Sachson Thomas
• Wang Yunzhen

Classifications

• G06F3/005

  Input arrangements through a video camera · CPC title

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G06T13/40 Primary

  of characters, e.g. humans, animals or virtual beings · CPC title

• G06F3/0304

  Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042) · CPC title

• G06F3/017

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title